© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 3111
    Prev
    Next
    INDEX
    Explanations

    instances of reporting on finding deceased individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "found" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.75
     tert
    -0.73
    creation
    -0.72
    dayName
    -0.70
    dos
    -0.64
    ankind
    -0.63
    entric
    -0.61
    annis
    -0.61
    adan
    -0.60
    idium
    -0.60
    POSITIVE LOGITS
    Ô
    0.88
    âĸĪ
    0.81
     guilty
    0.80
    dylib
    0.80
    ت
    0.79
    س
    0.74
    adle
    0.72
    mint
    0.71
     Guilty
    0.71
     dead
    0.70
    Activations Density 0.036%

    No Known Activations